Adversaries can create backdoored neural networks during outsourced training that maintain high accuracy on normal data but misbehave on attacker-chosen triggers.
Caffe Model Zoo
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2017 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
Adversaries can create backdoored neural networks during outsourced training that maintain high accuracy on normal data but misbehave on attacker-chosen triggers.